gui_act

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that high-risk actions require a confirmation token, which is valuable behavioral context. However, it does not mention potential side effects (e.g., navigation, state changes) or prerequisites like session validity. The token requirement is the only explicit behavioral trait.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise: a one-line summary followed by a clean parameter list. Each item earns its place, and the structure is easy to scan. No fluff or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 10 parameters and no annotations, the description covers all parameters and includes a safety note about high-risk actions. The output schema exists, so return values need not be described. Minor gaps remain, such as clarifying which actions are exactly 'high-risk' and whether a session must already exist, but overall it is sufficient for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description explicitly explains every parameter in the schema, including target, session_id, action, selector, x, y, text, url, reason, and confirm_token. It adds context by specifying allowed values for action and target, and clarifies that confirm_token is required for high-risk actions. This fully compensates for the schema's lack of descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states '执行 GUI 动作' (Execute GUI actions), with a specific verb and resource. It enumerates target types and action types, distinguishing it from the sibling tool gui_observe which is for observation. The scope is explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by naming targets and actions, but provides no explicit guidance on when to choose this tool over alternatives (e.g., gui_observe). It mentions the confirm token requirement for high-risk actions but does not compare with sibling tools. Context is present but alternatives are not addressed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.